Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2505.05864 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910934893592576 |
|---|---|
| author | Lee, Junhyeong Yuk, Jong Min Lee, Chan-Woo |
| author_facet | Lee, Junhyeong Yuk, Jong Min Lee, Chan-Woo |
| contents | The construction of experimental datasets is essential for expanding the scope of data-driven scientific discovery. Recent advances in natural language processing (NLP) have facilitated automatic extraction of structured data from unstructured scientific literature. While existing approaches-multi-step and direct methods-offer valuable capabilities, they also come with limitations when applied independently. Here, we propose a novel hybrid text-mining framework that integrates the advantages of both methods to convert unstructured scientific text into structured data. Our approach first transforms raw text into entity-recognized text, and subsequently into structured form. Furthermore, beyond the overall data structuring framework, we also enhance entity recognition performance by introducing an entity marker-a simple yet effective technique that uses symbolic annotations to highlight target entities. Specifically, our entity marker-based hybrid approach not only consistently outperforms previous entity recognition approaches across three benchmark datasets (MatScholar, SOFC, and SOFC slot NER) but also improve the quality of final structured data-yielding up to a 58% improvement in entity-level F1 score and up to 83% improvement in relation-level F1 score compared to direct approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_05864 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Symbol-based entity marker highlighting for enhanced text mining in materials science with generative AI Lee, Junhyeong Yuk, Jong Min Lee, Chan-Woo Computation and Language The construction of experimental datasets is essential for expanding the scope of data-driven scientific discovery. Recent advances in natural language processing (NLP) have facilitated automatic extraction of structured data from unstructured scientific literature. While existing approaches-multi-step and direct methods-offer valuable capabilities, they also come with limitations when applied independently. Here, we propose a novel hybrid text-mining framework that integrates the advantages of both methods to convert unstructured scientific text into structured data. Our approach first transforms raw text into entity-recognized text, and subsequently into structured form. Furthermore, beyond the overall data structuring framework, we also enhance entity recognition performance by introducing an entity marker-a simple yet effective technique that uses symbolic annotations to highlight target entities. Specifically, our entity marker-based hybrid approach not only consistently outperforms previous entity recognition approaches across three benchmark datasets (MatScholar, SOFC, and SOFC slot NER) but also improve the quality of final structured data-yielding up to a 58% improvement in entity-level F1 score and up to 83% improvement in relation-level F1 score compared to direct approach. |
| title | Symbol-based entity marker highlighting for enhanced text mining in materials science with generative AI |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2505.05864 |